SE3332 《机器学习》

SE2324 《计算机科学的数学基础》

Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human Programmers
Yuling Shi, Hongyu Zhang, Chengcheng Wan and Xiaodong Gu*
In Proceedings of the 47th International Conference on Software Engineering (ICSE 2025). Ottawa, Ontario, Canada, April 27 - May 3, 2025. (CCF-A)
[paper] [code] [bibtex]

On the Effectiveness of Large Language Models in Domain-Specific Code Generation
Xiaodong Gu*, Meng Chen, Yalan Lin, Yuhan Hu, Hongyu Zhang, Chengcheng Wan, Zhao Wei, Yong Xu, Juhong Wang
ACM Transactions on Software Engineering and Methodology (TOSEM 2024) (CCF-A)
[paper]

How Effectively Do Code Language Models Understand Poor-Readability Code?
Chao Hu, Yitian Chai, Hao Zhou, Fandong Meng, Jie Zhou and Xiaodong Gu*
In Proceedings of the 39th ACM/IEEE International Conference on Automated Software Engineering (ASE 2024). Sacramento, California, United States, Oct 27 - Nov 1, 2024. (CCF-A)
[paper] [code] [bibtex]

VarGAN: Adversarial Learning of Variable Semantic Representations
Yalan Lin, Chengcheng Wan, Shuwen Bai, Xiaodong Gu*
IEEE Transactions on Software Engineering (TSE 2024) (CCF-A)
[paper] [code]

On the Evaluation of Neural Code Translation: Taxonomy and Benchmark
Mingsheng Jiao, Tingrui Yu, Xuan Li, Guanjie Qiu, Xiaodong Gu*, Beijun Shen
In Proceedings of the 38th International Conference on Automated Software Engineering (ASE 2023), Kirchberg, Luxembourg, Sept. 11-15, 2023 (CCF-A)
[paper] [slides] [code]

InfeRE: Step-by-Step Regex Generation via Chain of Inference
Shuai Zhang, Xiaodong Gu, Yuting Chen, Beijun Shen
In Proceedings of the 38th International Conference on Automated Software Engineering (ASE 2023), Kirchberg, Luxembourg, Sept. 11-15, 2023 (CCF-A)
[paper] [slides] [code] [bibtex]

Self-Supervised Query Reformulation for Code Search
Yuetian Mao, Chengcheng Wan, Yuze Jiang, Xiaodong Gu*
In Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2023), San Francisco, California, United States, Dec 3-9, 2023 (CCF-A)
[paper] [slides] [code] [bibtex]

Diet Code Is Healthy: Simplifying Programs for Pre-Trained Models of Code
Zhaowei Zhang, Hongyu Zhang, Beijun Shen, Xiaodong Gu*
In Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2022), Singapore, Nov 14-18, 2022 (CCF-A)
[paper] [slides] [code] [bibtex]

Cross-Domain Deep Code Search with Meta Learning
Yitian Chai, Hongyu Zhang, Beijun Shen and Xiaodong Gu*
In Proceedings of the 44th International Conference on Software Engineering (ICSE 2022) (CCF-A)
[paper] [code] [slides] [bibtex]

• 上海自然科学基金面上项目，面向复杂场景的程序自动生成技术，2025.7-2028.6，主持

• CCF-华为胡杨林基金，针对问题单解决的Multi-Agent能力提升,2025.1.1-2025.7.31，主持

• 华为，场景知识增强的Java代码自动生成技术，2024.9.1-2025.2.25，主持

• 宁德时代，基于大模型的软件需求标准化技术，2024.6.1-2025.5.31，主持

• 宁德时代，基于大模型的测试用例转换技术，2024.6.1-2025.1.31，主持

• 宁德时代，基于大模型的变量模糊搜索技术，2024.6.1-2025.1.31，主持

• 国家重点研发计划，面向场景计算的低代码开发方法与环境，2023.12-2026.12，参与

• 中国航空无线电电子研究所，民机软件研制过程辅助系统，2022.12-2026.6，主持

• 1946伟德国际源自英国-华为密码学与数字信任创新实验室课题，基于大模型的恶意代码样本生成，2023.5.1-2024.4.31，主持

• CCF-腾讯犀牛鸟基金，特定领域程序自动生成，2022.10.1-2023.12.31，主持

• CCF-百度松果基金，基于预训练模型的程序表征，2021.9.1-2022.8.30，主持

• 国家自然科学基金，基于小样本学习的跨语言程序自动生成，2022.1.1-2024.12.31，主持